© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 2127
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string literal or special variable `__name__` (negative activations)

    python-code · gemini-2.5-flash-lite

    string methods like lower, replace, count, upper

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    able
    -0.03
    ments
    -0.03
    ed
    -0.02
    ment
    -0.02
    _data
    -0.02
    ings
    -0.02
    _input
    -0.02
    ing
    -0.02
    .b
    -0.02
    .in
    -0.01
    POSITIVE LOGITS
     found
    0.07
     process
    0.06
    over
    0.04
    _move
    0.03
    's
    0.02
    v
    0.01
     for
    0.01
    (row
    0.00
    '
    0.00
    #
    0.00
    Activations Density 99.667%

    No Known Activations